claude

dev-cycle

Development cycle orchestration: specify, plan, implement, review, integrate. A spec-capturer that interviews the owner, worktree-isolated implementers, spec and code-quality reviewers, and a review chain enforced by hooks.

4 on GitHubby ryzhakarv1.0.0MITupdated 23 days ago
/

Plugin dev-cycle from marketplace my-claude-skills in ryzhakar/claude-skills. Commands read from the repo's manifest — 23 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • dev-cycle

    Drive the specify, plan, implement, review, and integrate loop over software work through the spec-capturer, implementer, spec-reviewer, and code-quality-reviewer agents, as an extension of agentic-delegation. "specify and implement", "implement a feature end-to-end", "build this with agents", "orch

Subagents (4)

  • code-quality-reviewer

    Review the quality of a unit's changed code against the tdd skill's rules and the design checks below, and write a report file whose Ready to merge line gates the merge. Use it after the spec-reviewer has passed a unit, to audit a completed feature, or before merging code that must meet production s

  • implementer

    Use this agent to implement one unit from an implementation plan, carry out a well-specified coding task, or run a TDD cycle on a defined unit of work, inside its own git worktree. Examples: <example> Context: An implementation plan has five units. Unit 1 assigns the requirements of an authenticatio

  • spec-capturer

    Interview the owner through the AskUserQuestion tool, by the spec-chef skill's protocol, and turn a request into one specification file. Use it at the start of a development cycle before any plan exists, or when a request leaves product decisions implicit. Examples: <example> Context: The owner asks

  • spec-reviewer

    Verify that an implementation in a worktree matches its specification and write a verdict file reading PASS or FAIL. Use it after an implementer reports a unit complete, or when requirements and code may have drifted. Examples: <example> Context: An implementer agent has completed a unit and reporte

Hooks (5)

  • SubagentStop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/review-chain.py"

  • SubagentStop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/review-chain.py"

  • SubagentStop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/review-chain.py"

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/review-chain.py"

  • Stop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/review-chain.py"

View source on GitHub

More from ryzhakar/claude-skills

All 11 plugins →

instruction-eval

claude

Measure whether an LLM instruction changes model behavior.

11 skills

4

agent-conduct

claude

Domain-free skills governing how an agent conducts itself while working, independent of orchestration, memory, or any specific engineering domain.

6 skills · hooks

4

dev-cycle-lite

claude

Cost-tiered development cycle over dev-cycle: an opus prescriber writes prescriptions that leave no decision, a sonnet suborchestrator runs the loop and both reviews, disposable haiku executors follow the prescription literally. No hooks.

2 skills · 3 agents

4

dev-discipline

claude

Software engineering discipline skills, agent-agnostic: outermost-test-first signature-first TDD, systematic debugging, bug triage, architecture improvement, and receiving code review. Used ad hoc or by dev-cycle.

5 skills

4

qa-automation

claude

Playwright test lifecycle orchestrator. One skill drives the full loop: plan from live browser exploration, generate accessible .spec.ts files, execute with failure classification, and self-heal broken locators via deterministic ten-tier recovery with confidence-based PR routing.

1 skill · 4 agents

4

orchestration

claude

Agent delegation framework and multi-agent research orchestration. Decompose work across model tiers, manage parallel swarms, and govern quality.

2 skills

4

Similar plugins

diagram-design

claudecodex

Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.

1 skill · 7 commands

cathrynlavery/diagram-design 66,757

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

backend-development

claudecodex

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

ralph-skills

claude

PRD generation and conversion skills for the Ralph autonomous agent loop

2 skills

snarktank/ralph 22,224

superset

claude

Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.

14 skills · 1 command

superset-sh/superset 15,548

improve

claude

Point it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.

1 skill

shadcn/improve 11,576

Maintain dev-cycle?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins11 plugins